AI agents use place_footprint to create or update resources in Kicad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kicad environment.
Placing a footprint on a PCB modifies the design file reversibly—footprints can be moved or deleted later. This is a Write operation, not Destructive (no permanent deletion) or Execute (no arbitrary code execution). Severity is high because incorrect footprint placement could require significant rework of a PCB design, but the action itself is reversible.
From the tool's definition Tool name 'place_footprint' indicates placement of a footprint component on a PCB. Sibling tools like 'add_copper_zone', 'add_pcb_line', and 'add_pcb_text' are all Write operations that modify PCB designs.
Attacks that exploit this kind of access
place_footprint. It is categorised as a Write tool in the Kicad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kicad MCP server in PolicyLayer and add a rule for place_footprint: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kicad. Nothing to install.
place_footprint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the place_footprint rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for place_footprint. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
place_footprint is provided by the Kicad MCP server (productofamerica/mcp-server-kicad). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →